## 기초 명령어 실습 ##

1+1
1:10
dd = c(1:10)

## c()    -> 같은 종류의 요소(numeric, int, float등)만 있을때
## list() -> 다양한 종류의 요소가 들어올때

dd[-10]


## 기본유형 ##

x1 = 3                  # numeric
x2 = "Love is choice"   # character
x3 = FALSE              # logical
x4 = 3-2i               # complex
x5 = '123'              # character
x6 = 'false'            # character
x7 = 'FLASE'            # character

str(x1)

### 문자 - 정수 - 논리
### 결측값은 95%까지

### 정규분포는 30번이상한것으로 해야한다

xx1 <- c(1:100)
xx1
is.na(xx1)
table(is.na(xx1))

x1 = c(1,'love',TRUE,2+3i)
x1

v1 = c(27,35,47,41)
mode(v1)
is.numeric(v1)
is.na(v1)
table(is.na(v1))

v2 = c(27,35,47,NA,55)
mode(v2)
is.numeric(v2)
is.na(v2)
table(is.na(v2))

length(v1)
length(v2)

names(v1)
names(v1) = c('kim','lee','park','choi')

names(v1)

## Indexing ## 대괄호 == [ ] => 추출해라

v1
v1[1]
v1[1:3]
v1[-4]
v1[c(2,4)]

v1 = 1:3
v2 = 4:6
v3 = v1+v2 # can add list

v1 = 1:3
v2 = 1:6
v3 = v1+v2 # reusable add
v3

### 데이터거래사

## Factor, ordered Factor (등급을 정할 수 있는)

gender = c('m','f','f','m','f','f')
gender_factor = factor(gender)

levels(gender_factor)

gender_factor2 = factor(gender, levels = c('m','f'), labels = c('남자','여자'))
gender_factor2

gender_factor3 = factor(gender,ordered = TRUE)
gender_factor3


## Matrix ##
v1 = 1:3
v2 = 4:6
m1 = rbind(v1,v2)
m2 = cbind(v1,v2)
v1
v2
m1
m2

m1[2,1] == 8
m1[2,1] = 8
m1[,3]

is.na(m1)
table(is.na(m1))

m1[1,1] = NA
m1[2,3] = NA

table(is.na(m1))
str(m1)

m3 = matrix(1:4, nrow = 2, ncol = 2)
m4 = matrix(1:4, nrow = 2, ncol = 2, byrow = TRUE)
m3
m4[2,1] = NA


## array ##
a1 = array(1:10, dim=10)
a2 = array(1:10, dim=c(2, 5))
a3 = array(1:10, dim=c(3, 3, 4))

a1
a2
a3[,,2][3,3] = 100
a3

## DataFrame ##
id = 1:5
age = c(29, 32, 47, 35, 23)
gender = c('f','m','m','f','f')
height = c(163, 177, 172, 157, 169)
DF1 = data.frame(id, age, gender, height)
DF2 = data.frame(id, age, gender, height, stringsAsFactors=FALSE)
DF3 = data.frame(id, age, gender, height, stringsAsFactors=TRUE)
DF1
DF2
DF3

View(DF3)
str(DF3)

DF4 = DF3[-1]
DF4

View(DF4)
str(DF4)

## 기술통계량 ##
library(psych) # describe()명령어 호출 라이브러리

describe(DF4)

rownames(DF1) = paste('Edge',1:5,sep='_')
rownames(DF1)

colnames(DF1) = paste(c('아이디','나이','성별','키'))
colnames(DF1)

dim(DF1)

searchpaths()

## read text data ##
k200 = read.csv(file = './data/k100.csv',header = TRUE)
k300 = read.csv(file = './data/ebook.csv',header = TRUE)
tsv100 = read.table(file = './data/survey_tab.txt', header = TRUE, fileEncoding = 'CP949')

## data handling ##
library(ggplot2)

head(diamonds)
View(diamonds)
head(Titanic)
View(Titanic)

## data structure ##
str(diamonds)
str(Titanic)

## indexing ##
diamonds[ , 2]
diamonds[ , 2, drop=FALSE]
xx = diamonds[ , c(2, 3, 7)]            # 2,3,7번째 값 추출
ss = diamonds[,7]                       # 7번째 값 추출
describe(diamonds)                      # 기술통계량
diamonds[ , 7:10]
diamonds[ , seq(from=2, to=10, by=2)]

diamonds[ , 'cut']
diamonds[ , c('cut', 'price')]

## 행추출하기 ##
a = diamonds[diamonds$cut == 'Fair', ]
a
b = diamonds[diamonds$price >= 18000, ]  # 다이아몬드의 가격을 기준으로 추출
b
c = diamonds[(diamonds$cut == 'Fair') & (diamonds$price >= 18000), ]
d = diamonds[(diamonds$cut == 'Fair') | (diamonds$price >= 18000), ]